html_tokenizer 0.0.6 → 0.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: cf47920a7a89b9806ac9b1e830b6965e2ec0e98e
-  data.tar.gz: 97dbc221ee255a3d6a9d17f20e1807cdddec3eb3
+SHA256:
+  metadata.gz: 2bd91c4080202f5c9d62d494f843f73a3f12c24a24d1408bc09495a161756d4e
+  data.tar.gz: 484eba0fbc765e4894d63d60cbcc335032278d8699f56888e00f1782c4bd1466
 SHA512:
-  metadata.gz: e9865b029658f9ad0186863319ecbb9a9d62f7de43b7763c91f455848c79cfd0fed2008f5f86d7b79b5434a97b547464716e5a9ebb67ac6248ceec5b8c85cd4a
-  data.tar.gz: 0c092d6501187b4eff8d0981831b3df3a25b957516c138b7989ae57c92c139ade5952a90df7f80ed928252c724de9cc2bc37d0921540d4da0d1bd13faf6462aa
+  metadata.gz: 3b6a469d11e44df8898e1e30e18ae6048974691de52de34b3a9c781598145f42415d2a738337a587b4fc86853f06c6acf7f20e86e972ec96016dea37ae9291b2
+  data.tar.gz: 24622424f4abc8ee5ea2cc519024391ca8ef8c49d2c7f29d080256137e34284e64a7cf2b768fb6d773e987f40cf3cdf854e994dd812bf2719efda3f60414af9c

data/.github/workflows/ci.yml

@@ -0,0 +1,19 @@
+name: CI
+on: [push]
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby: [ '2.5', '2.6', '2.7', '3.0', '3.1', '3.2', '3.3' ]
+    name: Ruby ${{ matrix.ruby }} Tests
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+          bundler-cache: true
+      - name: Run tests
+        run: bundle exec rake

data/.gitignore

@@ -1,6 +1,8 @@
+Gemfile.lock
 *.bundle
 tmp/
 
+
 # Object files
 *.o
 *.ko

data/ext/html_tokenizer_ext/extconf.rb

@@ -1,8 +1,8 @@
 require 'mkmf'
 
 $CXXFLAGS += " -std=c++11 "
-$CXXFLAGS += " -g -Og -ggdb "
-$CFLAGS += " -g -Og -ggdb "
+$CXXFLAGS += " -g -O1 -ggdb "
+$CFLAGS += " -g -O1 -ggdb "
 
 if ENV['DEBUG']
   $CXXFLAGS += "  -DDEBUG "

data/ext/html_tokenizer_ext/parser.c

@@ -455,8 +455,8 @@ static void parser_tokenize_callback(struct tokenizer_t *tk, enum token_type typ
     enc = rb_enc_from_index(parser->doc.enc_index);
     mb_strlen = rb_enc_strlen(parser->doc.data + ref.start, parser->doc.data + ref.start + ref.length, enc);
     rb_yield_values(5, token_type_to_symbol(type),
-      INT2NUM(ref.mb_start), INT2NUM(ref.mb_start + mb_strlen),
-      INT2NUM(ref.line_number), INT2NUM(ref.column_number));
+      ULONG2NUM(ref.mb_start), ULONG2NUM(ref.mb_start + mb_strlen),
+      ULONG2NUM(ref.line_number), ULONG2NUM(ref.column_number));
   }
 
   parser_adjust_line_number(parser, ref.start, ref.length);
@@ -495,7 +495,10 @@ static VALUE parser_initialize_method(VALUE self)
 
 static int parser_document_append(struct parser_t *parser, const char *string, unsigned long int length)
 {
+#ifdef DEBUG
   void *old = parser->doc.data;
+#endif
+
   unsigned long int mb_length;
   char *buf;
   rb_encoding *enc = rb_enc_from_index(parser->doc.enc_index);
@@ -718,7 +721,7 @@ static VALUE parser_errors_count_method(VALUE self)
 {
   struct parser_t *parser = NULL;
   Parser_Get_Struct(self, parser);
-  return INT2NUM(parser->errors_count);
+  return ULONG2NUM(parser->errors_count);
 }
 
 static VALUE create_parser_error(struct parser_document_error_t *error)
@@ -734,7 +737,7 @@ static VALUE create_parser_error(struct parser_document_error_t *error)
   return rb_class_new_instance(4, args, klass);
 }
 
-static VALUE parser_errors_method(VALUE self, VALUE error_p)
+static VALUE parser_errors_method(VALUE self)
 {
   struct parser_t *parser = NULL;
   VALUE list;

data/ext/html_tokenizer_ext/tokenizer.c

@@ -135,7 +135,7 @@ static void tokenizer_yield_tag(struct tokenizer_t *tk, enum token_type type, lo
 {
   long unsigned int mb_length = tokenizer_mblength(tk, length);
   tk->last_token = type;
-  rb_yield_values(3, token_type_to_symbol(type), INT2NUM(tk->scan.mb_cursor), INT2NUM(tk->scan.mb_cursor + mb_length));
+  rb_yield_values(3, token_type_to_symbol(type), ULONG2NUM(tk->scan.mb_cursor), ULONG2NUM(tk->scan.mb_cursor + mb_length));
 }
 
 static void tokenizer_callback(struct tokenizer_t *tk, enum token_type type, long unsigned int length)
@@ -464,11 +464,9 @@ static int scan_tag_name(struct tokenizer_t *tk)
 {
   unsigned long int length = 0, tag_name_length = 0;
   const char *tag_name = NULL;
-  void *old;
 
   if(is_tag_name(&tk->scan, &tag_name, &tag_name_length)) {
     length = (tk->current_tag ? strlen(tk->current_tag) : 0);
-    old = tk->current_tag;
     REALLOC_N(tk->current_tag, char, length + tag_name_length + 1);
     DBG_PRINT("tk=%p realloc(tk->current_tag) %p -> %p length=%lu", tk, old,
       tk->current_tag,  length + tag_name_length + 1);
@@ -664,7 +662,6 @@ void tokenizer_scan_all(struct tokenizer_t *tk)
 
 void tokenizer_set_scan_string(struct tokenizer_t *tk, const char *string, long unsigned int length)
 {
-  const char *old = tk->scan.string;
   REALLOC_N(tk->scan.string, char, string ? length + 1 : 0);
   DBG_PRINT("tk=%p realloc(tk->scan.string) %p -> %p length=%lu", tk, old,
     tk->scan.string, length + 1);

data/html_tokenizer.gemspec

@@ -1,9 +1,21 @@
+# frozen_string_literal: true
+
+require_relative "lib/html_tokenizer/version"
+
 Gem::Specification.new do |spec|
   spec.name    = "html_tokenizer"
-  spec.version = "0.0.6"
+  spec.version = HtmlTokenizer::VERSION
   spec.summary = "HTML Tokenizer"
   spec.author  = "Francois Chagnon"
 
+  spec.homepage      = "https://github.com/Shopify/html_tokenizer"
+  spec.license       = "MIT"
+
+  spec.metadata["allowed_push_host"] = "https://rubygems.org/"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+
   spec.files = Dir.glob("ext/**/*.{c,h,rb}") +
             Dir.glob("lib/**/*.rb")
 
@@ -12,8 +24,4 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib", "ext"]
-
-  spec.add_development_dependency 'rake', '~> 0'
-  spec.add_development_dependency 'rake-compiler', '~> 0'
-  spec.add_development_dependency 'minitest', '~> 0'
 end

data/lib/html_tokenizer/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module HtmlTokenizer
+  VERSION = "0.0.8"
+end

data/lib/html_tokenizer.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'html_tokenizer_ext'
 
 module HtmlTokenizer

metadata

@@ -1,59 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: html_tokenizer
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.8
 platform: ruby
 authors:
 - Francois Chagnon
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-01-23 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake-compiler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: minitest
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0'
-description: 
-email: 
+date: 2024-03-20 00:00:00.000000000 Z
+dependencies: []
+description:
+email:
 executables:
 - html_tokenizer
 extensions:
@@ -61,9 +19,9 @@ extensions:
 extra_rdoc_files: []
 files:
 - ".autotest"
+- ".github/workflows/ci.yml"
 - ".gitignore"
 - Gemfile
-- Gemfile.lock
 - LICENSE
 - Manifest.txt
 - README.md
@@ -78,12 +36,17 @@ files:
 - ext/html_tokenizer_ext/tokenizer.h
 - html_tokenizer.gemspec
 - lib/html_tokenizer.rb
+- lib/html_tokenizer/version.rb
 - test/unit/parser_test.rb
 - test/unit/tokenizer_test.rb
-homepage: 
-licenses: []
-metadata: {}
-post_install_message: 
+homepage: https://github.com/Shopify/html_tokenizer
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org/
+  homepage_uri: https://github.com/Shopify/html_tokenizer
+  source_code_uri: https://github.com/Shopify/html_tokenizer
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -99,9 +62,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.14
-signing_key: 
+rubygems_version: 3.5.5
+signing_key:
 specification_version: 4
 summary: HTML Tokenizer
 test_files:

data/Gemfile.lock

@@ -1,24 +0,0 @@
-PATH
-  remote: .
-  specs:
-    html_tokenizer (0.0.6)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    minitest (5.9.0)
-    rake (12.3.0)
-    rake-compiler (0.9.9)
-      rake
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  html_tokenizer!
-  minitest
-  rake
-  rake-compiler
-
-BUNDLED WITH
-   1.16.0